bitmap.c

来自「linux 内核源代码」· C语言 代码 · 共 1,568 行 · 第 1/3 页

	} else {
		bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset, 0);
	}
	if (IS_ERR(bitmap->sb_page)) {
		err = PTR_ERR(bitmap->sb_page);
		bitmap->sb_page = NULL;
		return err;
	}

	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);

	chunksize = le32_to_cpu(sb->chunksize);
	daemon_sleep = le32_to_cpu(sb->daemon_sleep);
	write_behind = le32_to_cpu(sb->write_behind);

	/* verify that the bitmap-specific fields are valid */
	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
		reason = "bad magic";
	else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO ||
		 le32_to_cpu(sb->version) > BITMAP_MAJOR_HI)
		reason = "unrecognized superblock version";
	else if (chunksize < PAGE_SIZE)
		reason = "bitmap chunksize too small";
	else if ((1 << ffz(~chunksize)) != chunksize)
		reason = "bitmap chunksize not a power of 2";
	else if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT / HZ)
		reason = "daemon sleep period out of range";
	else if (write_behind > COUNTER_MAX)
		reason = "write-behind limit out of range (0 - 16383)";
	if (reason) {
		printk(KERN_INFO "%s: invalid bitmap file superblock: %s\n",
			bmname(bitmap), reason);
		goto out;
	}

	/* keep the array size field of the bitmap superblock up to date */
	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);

	if (!bitmap->mddev->persistent)
		goto success;

	/*
	 * if we have a persistent array superblock, compare the
	 * bitmap's UUID and event counter to the mddev's
	 */
	if (memcmp(sb->uuid, bitmap->mddev->uuid, 16)) {
		printk(KERN_INFO "%s: bitmap superblock UUID mismatch\n",
			bmname(bitmap));
		goto out;
	}
	events = le64_to_cpu(sb->events);
	if (events < bitmap->mddev->events) {
		printk(KERN_INFO "%s: bitmap file is out of date (%llu < %llu) "
			"-- forcing full recovery\n", bmname(bitmap), events,
			(unsigned long long) bitmap->mddev->events);
		sb->state |= cpu_to_le32(BITMAP_STALE);
	}
success:
	/* assign fields using values from superblock */
	bitmap->chunksize = chunksize;
	bitmap->daemon_sleep = daemon_sleep;
	bitmap->daemon_lastrun = jiffies;
	bitmap->max_write_behind = write_behind;
	bitmap->flags |= le32_to_cpu(sb->state);
	if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN)
		bitmap->flags |= BITMAP_HOSTENDIAN;
	bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
	if (sb->state & cpu_to_le32(BITMAP_STALE))
		bitmap->events_cleared = bitmap->mddev->events;
	err = 0;
out:
	kunmap_atomic(sb, KM_USER0);
	if (err)
		bitmap_print_sb(bitmap);
	return err;
}

enum bitmap_mask_op {
	MASK_SET,
	MASK_UNSET
};

/* record the state of the bitmap in the superblock.  Return the old value */
static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
			     enum bitmap_mask_op op)
{
	bitmap_super_t *sb;
	unsigned long flags;
	int old;

	spin_lock_irqsave(&bitmap->lock, flags);
	if (!bitmap->sb_page) { /* can't set the state */
		spin_unlock_irqrestore(&bitmap->lock, flags);
		return 0;
	}
	spin_unlock_irqrestore(&bitmap->lock, flags);
	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
	old = le32_to_cpu(sb->state) & bits;
	switch (op) {
		case MASK_SET: sb->state |= cpu_to_le32(bits);
				break;
		case MASK_UNSET: sb->state &= cpu_to_le32(~bits);
				break;
		default: BUG();
	}
	kunmap_atomic(sb, KM_USER0);
	return old;
}

/*
 * general bitmap file operations
 */

/* calculate the index of the page that contains this bit */
static inline unsigned long file_page_index(unsigned long chunk)
{
	return CHUNK_BIT_OFFSET(chunk) >> PAGE_BIT_SHIFT;
}

/* calculate the (bit) offset of this bit within a page */
static inline unsigned long file_page_offset(unsigned long chunk)
{
	return CHUNK_BIT_OFFSET(chunk) & (PAGE_BITS - 1);
}

/*
 * return a pointer to the page in the filemap that contains the given bit
 *
 * this lookup is complicated by the fact that the bitmap sb might be exactly
 * 1 page (e.g., x86) or less than 1 page -- so the bitmap might start on page
 * 0 or page 1
 */
static inline struct page *filemap_get_page(struct bitmap *bitmap,
					unsigned long chunk)
{
	if (file_page_index(chunk) >= bitmap->file_pages) return NULL;
	return bitmap->filemap[file_page_index(chunk) - file_page_index(0)];
}


static void bitmap_file_unmap(struct bitmap *bitmap)
{
	struct page **map, *sb_page;
	unsigned long *attr;
	int pages;
	unsigned long flags;

	spin_lock_irqsave(&bitmap->lock, flags);
	map = bitmap->filemap;
	bitmap->filemap = NULL;
	attr = bitmap->filemap_attr;
	bitmap->filemap_attr = NULL;
	pages = bitmap->file_pages;
	bitmap->file_pages = 0;
	sb_page = bitmap->sb_page;
	bitmap->sb_page = NULL;
	spin_unlock_irqrestore(&bitmap->lock, flags);

	while (pages--)
		if (map[pages]->index != 0) /* 0 is sb_page, release it below */
			free_buffers(map[pages]);
	kfree(map);
	kfree(attr);

	if (sb_page)
		free_buffers(sb_page);
}

static void bitmap_file_put(struct bitmap *bitmap)
{
	struct file *file;
	unsigned long flags;

	spin_lock_irqsave(&bitmap->lock, flags);
	file = bitmap->file;
	bitmap->file = NULL;
	spin_unlock_irqrestore(&bitmap->lock, flags);

	if (file)
		wait_event(bitmap->write_wait,
			   atomic_read(&bitmap->pending_writes)==0);
	bitmap_file_unmap(bitmap);

	if (file) {
		struct inode *inode = file->f_path.dentry->d_inode;
		invalidate_mapping_pages(inode->i_mapping, 0, -1);
		fput(file);
	}
}


/*
 * bitmap_file_kick - if an error occurs while manipulating the bitmap file
 * then it is no longer reliable, so we stop using it and we mark the file
 * as failed in the superblock
 */
static void bitmap_file_kick(struct bitmap *bitmap)
{
	char *path, *ptr = NULL;

	if (bitmap_mask_state(bitmap, BITMAP_STALE, MASK_SET) == 0) {
		bitmap_update_sb(bitmap);

		if (bitmap->file) {
			path = kmalloc(PAGE_SIZE, GFP_KERNEL);
			if (path)
				ptr = file_path(bitmap->file, path, PAGE_SIZE);

			printk(KERN_ALERT
			      "%s: kicking failed bitmap file %s from array!\n",
			      bmname(bitmap), ptr ? ptr : "");

			kfree(path);
		} else
			printk(KERN_ALERT
			       "%s: disabling internal bitmap due to errors\n",
			       bmname(bitmap));
	}

	bitmap_file_put(bitmap);

	return;
}

enum bitmap_page_attr {
	BITMAP_PAGE_DIRTY = 0, // there are set bits that need to be synced
	BITMAP_PAGE_CLEAN = 1, // there are bits that might need to be cleared
	BITMAP_PAGE_NEEDWRITE=2, // there are cleared bits that need to be synced
};

static inline void set_page_attr(struct bitmap *bitmap, struct page *page,
				enum bitmap_page_attr attr)
{
	__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
}

static inline void clear_page_attr(struct bitmap *bitmap, struct page *page,
				enum bitmap_page_attr attr)
{
	__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
}

static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *page,
					   enum bitmap_page_attr attr)
{
	return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
}

/*
 * bitmap_file_set_bit -- called before performing a write to the md device
 * to set (and eventually sync) a particular bit in the bitmap file
 *
 * we set the bit immediately, then we record the page number so that
 * when an unplug occurs, we can flush the dirty pages out to disk
 */
static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
{
	unsigned long bit;
	struct page *page;
	void *kaddr;
	unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap);

	if (!bitmap->filemap) {
		return;
	}

	page = filemap_get_page(bitmap, chunk);
	if (!page) return;
	bit = file_page_offset(chunk);

 	/* set the bit */
	kaddr = kmap_atomic(page, KM_USER0);
	if (bitmap->flags & BITMAP_HOSTENDIAN)
		set_bit(bit, kaddr);
	else
		ext2_set_bit(bit, kaddr);
	kunmap_atomic(kaddr, KM_USER0);
	PRINTK("set file bit %lu page %lu\n", bit, page->index);

	/* record page number so it gets flushed to disk when unplug occurs */
	set_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);

}

/* this gets called when the md device is ready to unplug its underlying
 * (slave) device queues -- before we let any writes go down, we need to
 * sync the dirty pages of the bitmap file to disk */
void bitmap_unplug(struct bitmap *bitmap)
{
	unsigned long i, flags;
	int dirty, need_write;
	struct page *page;
	int wait = 0;

	if (!bitmap)
		return;

	/* look at each page to see if there are any set bits that need to be
	 * flushed out to disk */
	for (i = 0; i < bitmap->file_pages; i++) {
		spin_lock_irqsave(&bitmap->lock, flags);
		if (!bitmap->filemap) {
			spin_unlock_irqrestore(&bitmap->lock, flags);
			return;
		}
		page = bitmap->filemap[i];
		dirty = test_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
		need_write = test_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
		clear_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
		clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
		if (dirty)
			wait = 1;
		spin_unlock_irqrestore(&bitmap->lock, flags);

		if (dirty | need_write)
			write_page(bitmap, page, 0);
	}
	if (wait) { /* if any writes were performed, we need to wait on them */
		if (bitmap->file)
			wait_event(bitmap->write_wait,
				   atomic_read(&bitmap->pending_writes)==0);
		else
			md_super_wait(bitmap->mddev);
	}
	if (bitmap->flags & BITMAP_WRITE_ERROR)
		bitmap_file_kick(bitmap);
}

static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed);
/* * bitmap_init_from_disk -- called at bitmap_create time to initialize
 * the in-memory bitmap from the on-disk bitmap -- also, sets up the
 * memory mapping of the bitmap file
 * Special cases:
 *   if there's no bitmap file, or if the bitmap file had been
 *   previously kicked from the array, we mark all the bits as
 *   1's in order to cause a full resync.
 *
 * We ignore all bits for sectors that end earlier than 'start'.
 * This is used when reading an out-of-date bitmap...
 */
static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
{
	unsigned long i, chunks, index, oldindex, bit;
	struct page *page = NULL, *oldpage = NULL;
	unsigned long num_pages, bit_cnt = 0;
	struct file *file;
	unsigned long bytes, offset;
	int outofdate;
	int ret = -ENOSPC;
	void *paddr;

	chunks = bitmap->chunks;
	file = bitmap->file;

	BUG_ON(!file && !bitmap->offset);

#ifdef INJECT_FAULTS_3
	outofdate = 1;
#else
	outofdate = bitmap->flags & BITMAP_STALE;
#endif
	if (outofdate)
		printk(KERN_INFO "%s: bitmap file is out of date, doing full "
			"recovery\n", bmname(bitmap));

	bytes = (chunks + 7) / 8;

	num_pages = (bytes + sizeof(bitmap_super_t) + PAGE_SIZE - 1) / PAGE_SIZE;

	if (file && i_size_read(file->f_mapping->host) < bytes + sizeof(bitmap_super_t)) {
		printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",
			bmname(bitmap),
			(unsigned long) i_size_read(file->f_mapping->host),
			bytes + sizeof(bitmap_super_t));
		goto err;
	}

	ret = -ENOMEM;

	bitmap->filemap = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL);
	if (!bitmap->filemap)
		goto err;

	/* We need 4 bits per page, rounded up to a multiple of sizeof(unsigned long) */
	bitmap->filemap_attr = kzalloc(
		roundup( DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
		GFP_KERNEL);
	if (!bitmap->filemap_attr)
		goto err;

	oldindex = ~0L;

	for (i = 0; i < chunks; i++) {
		int b;
		index = file_page_index(i);
		bit = file_page_offset(i);
		if (index != oldindex) { /* this is a new page, read it in */
			int count;
			/* unmap the old page, we're done with it */
			if (index == num_pages-1)
				count = bytes + sizeof(bitmap_super_t)
					- index * PAGE_SIZE;
			else
				count = PAGE_SIZE;
			if (index == 0) {
				/*
				 * if we're here then the superblock page
				 * contains some bits (PAGE_SIZE != sizeof sb)
				 * we've already read it in, so just use it
				 */
				page = bitmap->sb_page;
				offset = sizeof(bitmap_super_t);
			} else if (file) {
				page = read_page(file, index, bitmap, count);
				offset = 0;
			} else {
				page = read_sb_page(bitmap->mddev, bitmap->offset, index);
				offset = 0;
			}
			if (IS_ERR(page)) { /* read error */
				ret = PTR_ERR(page);
				goto err;
			}

			oldindex = index;
			oldpage = page;

			if (outofdate) {
				/*
				 * if bitmap is out of date, dirty the
			 	 * whole page and write it out
				 */
				paddr = kmap_atomic(page, KM_USER0);
				memset(paddr + offset, 0xff,
				       PAGE_SIZE - offset);
				kunmap_atomic(paddr, KM_USER0);
				write_page(bitmap, page, 1);

				ret = -EIO;
				if (bitmap->flags & BITMAP_WRITE_ERROR) {
					/* release, page not in filemap yet */
					put_page(page);
					goto err;
				}
			}

			bitmap->filemap[bitmap->file_pages++] = page;
			bitmap->last_page_size = count;
		}
		paddr = kmap_atomic(page, KM_USER0);
		if (bitmap->flags & BITMAP_HOSTENDIAN)
			b = test_bit(bit, paddr);
		else
			b = ext2_test_bit(bit, paddr);
		kunmap_atomic(paddr, KM_USER0);
		if (b) {
			/* if the disk bit is set, set the memory bit */
			bitmap_set_memory_bits(bitmap, i << CHUNK_BLOCK_SHIFT(bitmap),
					       ((i+1) << (CHUNK_BLOCK_SHIFT(bitmap)) >= start)
				);
			bit_cnt++;
			set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
		}
	}

 	/* everything went OK */
	ret = 0;
	bitmap_mask_state(bitmap, BITMAP_STALE, MASK_UNSET);

	if (bit_cnt) { /* Kick recovery if any bits were set */
		set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery);
		md_wakeup_thread(bitmap->mddev->thread);
	}

	printk(KERN_INFO "%s: bitmap initialized from disk: "
		"read %lu/%lu pages, set %lu bits\n",
		bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt);

	return 0;

 err:
	printk(KERN_INFO "%s: bitmap initialisation failed: %d\n",
	       bmname(bitmap), ret);
	return ret;
}

void bitmap_write_all(struct bitmap *bitmap)
{
	/* We don't actually write all bitmap blocks here,
	 * just flag them as needing to be written
	 */
	int i;

	for (i=0; i < bitmap->file_pages; i++)
		set_page_attr(bitmap, bitmap->filemap[i],
			      BITMAP_PAGE_NEEDWRITE);
}


static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
{
	sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap);
	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
	bitmap->bp[page].count += inc;
/*
	if (page == 0) printk("count page 0, offset %llu: %d gives %d\n",
			      (unsigned long long)offset, inc, bitmap->bp[page].count);
*/
	bitmap_checkfree(bitmap, page);
}
static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
					    sector_t offset, int *blocks,
					    int create);

/*
 * bitmap daemon -- periodically wakes up to clean bits and flush pages
 *			out to disk
 */

void bitmap_daemon_work(struct bitmap *bitmap)
{
	unsigned long j;
	unsigned long flags;